检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Schmidt, Sebastian Günnemann, Stephan BMW Group Munich Germany Technical University of Munich Data Analytics and Machine Learning Group Munich Germany

Active learning (AL) reduces the amount of labeled data needed to train a machine learning model by intelligently choosing which instances to label. Classic pool-based AL requires all data to be present in a datacenter, which can be challenging with the increasing amounts of data needed in deep learning. However, AL on mobile devices and robots, like autonomous cars, can filter the data from perception sensor streams before reaching the datacenter. We exploited the temporal properties for such image streams in our work and proposed the novel temporal predicted loss (TPL)1 method. To evaluate the stream-based setting properly, we introduced the GTA V streets and the A2D2 streets dataset and made both publicly available. Our experiments showed that our approach significantly improves the diversity of the selection while being an uncertainty-based method. As pool-based approaches are more common in perception applications, we derived a concept for comparing pool-based and stream-based AL, where TPL outperformed state-of-the-art pool- or stream-based approaches for different models. TPL demonstrated a gain of 2.5 precept points (pp) less required data while being significantly faster than pool-based methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

FewSOME: One-Class Few Shot Anomaly Detection with Siamese Networks

FewSOME: One-Class Few Shot Anomaly Detection with Siamese N...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Belton, Niamh Hagos, Misgina Tsighe Lawlor, Aonghus Curran, Kathleen M. Science Foundation Ireland Centre for Research Training in Machine Learning Ireland University College Dublin School of Medicine Ireland University College Dublin School of Computer Science Ireland University College Dublin Insight Centre for Data Analytics Dublin Ireland

ISBN: (纸本)9798350302493

Recent Anomaly Detection techniques have progressed the field considerably but at the cost of increasingly complex training pipelines. Such techniques require large amounts of training data, resulting in computationally expensive algorithms that are unsuitable for settings where only a small amount of normal samples are available for training. We propose 'Few Shot anOMaly dEtection' (FewSOME), a deep One-Class Anomaly Detection algorithm with the ability to accurately detect anomalies having trained on 'few' examples of the normal class and no examples of the anomalous class. We describe FewSOME to be of low complexity given its low data requirement and short training time. FewSOME is aided by pretrained weights with an architecture based on Siamese Networks. By means of an ablation study, we demonstrate how our proposed loss, 'Stop Loss', improves the robustness of FewSOME. Our experiments demonstrate that FewSOME performs at stateof-the-art level on benchmark datasets MNIST, CIFAR-10, F-MNIST and MVTec AD while training on only 30 normal samples, a minute fraction of the data that existing methods are trained on. Moreover, our experiments show FewSOME to be robust to contaminated datasets. We also report F1 score and balanced accuracy in addition to AUC as a benchmark for future techniques to be compared against. Code available;https://***/niamhbelton/FewSOME. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

ConvLoRA and AdaBN Based Domain Adaptation via Self-Training

ConvLoRA and AdaBN Based Domain Adaptation via Self-Training

引用

IEEE International Symposium on Biomedical Imaging

作者： Sidra Aleem Julia Dietlmeier Eric Arazo Suzanne Little SFI Research Centre for Machine Learning Dublin City University Ireland Insight SFI Research Centre for Data Analytics Dublin City University Ireland

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Existing domain adaptation (DA) methods often involve pre-training on the source domain and fine-tuning on the target domain. For multi-target domain adaptation, having a dedicated/separate fine-tuned network for each target domain, that retain all the pre-trained model parameters, is prohibitively expensive. To address this limitation, we propose Convolutional Low-Rank Adaptation (ConvLoRA). ConvLoRA freezes pre-trained model weights, adds trainable low-rank decomposition matrices to convolutional layers, and backpropagates the gradient through these matrices thus greatly reducing the number of trainable parameters. To further boost adaptation, we utilize Adaptive Batch Normalization (AdaBN) which computes target-specific running statistics and use it along with ConvLoRA. Our method has fewer trainable parameters and performs better or on-par with large independent fine-tuned networks (with less than 0.9% trainable parameters of the total base model) when tested on the segmentation of Calgary-Campinas dataset containing brain MRI images. Our approach is simple, yet effective and can be applied to any deep learning-based architecture which uses convolutional and batch normalization layers. Code is available at: https://***/aleemsidra/ConvLoRA.

关键词： Convolutional codes Adaptation models Image segmentation Computational modeling Magnetic resonance imaging Matrix decomposition Batch normalization

来源：评论

学校读者我要写书评

暂无评论

The map equation goes neural: mapping network flows with graph neural networks 24

The map equation goes neural: mapping network flows with gra...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Christopher Blöcker Chester Tan Ingo Scholtes Data Analytics Group Department of Informatics University of Zurich Switzerland Chair of Machine Learning for Complex Networks Center for Artificial Intelligence and Data Science Julius-Maximilians-Universität Würzburg Germany

ISBN: (纸本)9798331314385

Community detection is an essential tool for unsupervised data exploration and revealing the organisational structure of networked systems. With a long history in network science, community detection typically relies on objective functions, optimised with custom-tailored search algorithms, but often without leveraging recent advances in deep learning. Recently, first works have started incorporating such objectives into loss functions for deep graph clustering and pooling. We consider the map equation, a popular information-theoretic objective function for unsupervised community detection, and express it in differentiable tensor form for optimisation through gradient descent. Our formulation turns the map equation compatible with any neural network architecture, enables end-to-end learning, incorporates node features, and chooses the optimal number of clusters automatically, all without requiring explicit regularisation. Applied to unsupervised graph clustering tasks, we achieve competitive performance against state-of-the-art deep graph clustering baselines in synthetic and real-world datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a data Governance Framework and Platform: A Case Study of a National Research Organization of Thailand 20

Design and Implementation of a Data Governance Framework and...

引用

20th International Joint Conference on Computer Science and Software Engineering, JCSSE 2023

作者： Chanyachatchawan, Sapa Nasingkun, Krich Tumsangthong, Patipat Chata, Porntiwa Buranarach, Marut Socharoentum, Monsak National Electronics and Computer Technology Center Leveraging Technology Solutions Section Bangkok Thailand National Electronics and Computer Technology Center Strategic Analytics Networks with Machine Learning and Ai Research Bangkok Thailand National Electronics and Computer Technology Center Data Science and Analytics Research Group Bangkok Thailand Digital Government Development Agency Bangkok Thailand

ISBN: (纸本)9798350300505

In the current era of extensive data usage across industries, data collection, preservation, utilization, and organization has become more challenging and nuanced because it is necessary to consider critical concerns such as data security, privacy, and legal issues, apart from efficiency issues. As a result, Thai government initiated the idea and effort to implement data governance throughout the government agency. This paper showcases the implementation of data governance in a governmental research organization with highly diverse structured and unstructured data. The implementation follows international standards and the guidelines of the Digital Government Development Agency (DGA). The executives set up the working body, including the data Governance Council and data Stewards, responsible for setting up and deploying policies and regulations. Creating awareness and the necessary infrastructure are the main focuses in the first-year phase. The metadata was designed to extend DGA's version and match the organization's unique requirements. A data catalog platform was developed accordingly. We organized activities to boost employee awareness and participation, including advertising and data catalog platform training. By the end of the first year of implementation, every organization unit had registered at least one data record into the data catalog. © 2023 IEEE.

关键词： Metadata

来源：评论

学校读者我要写书评

暂无评论

Estimating fish weight growth in aquaponic farming through machine learning techniques

Estimating fish weight growth in aquaponic farming through m...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Purushottam Kumar Pranav Tiwari U Srinivasulu Reddy CoE in Artificial Intelligence Machine Learning & Data Analytics Lab National Institute of Technology Trichy India Computer Science and Engineering Indian Institute of Information Technology Tiruchirappalli Trichy India Department of Computer Applications Machine Learning & Data Analytics Lab National Institute of Technology Trichy India

Due to the ever-growing population, rapid urbanization, unusual environmental change, and dwindling water supply, the food production from conventional farming techniques won’t be able to keep up with increasing food demand for long, leading to severe food scarcity. Aquaponics is emerging as a viable alternative to food cultivation techniques but lacks efficiency, hindering its adoption on a large-scale production basis. The adoption of Artificial Intelligence (AI) techniques in smart aquaponic farming can further contribute to increasing the yield in aquaponics. In the study, both linear and non-linear regression algorithms such as linear regression, lasso regression, ridge regression, KNN regression, SVR, and decision tree regression were trained on aquaponic fish pond dataset, evaluated on the basis of multiple metrics like MAE, MSE, RMSE, and RMSLE, and a competitive analysis was done to determine the best algorithm for predicting the harvest weight of the fish in aquaponic ponds. The results showed that KNN regression and decision tree regression algorithms have lowest error and highest accuracy of 99.15% and 99.1% respectively, for predicting the harvest weight of the fish. The results obtained could be scaled up to commercial levels and used in regulating nutrient concentration and aquatic environmental conditions

关键词：

来源：评论

学校读者我要写书评

暂无评论

Harnessing Ensemble machine learning Models for Timely Diagnosis of Breast Cancer Metastasis: A Case Study on CatBoost, XGBoost, and LGBM

Harnessing Ensemble Machine Learning Models for Timely Diagn...

引用

Annual Siberian Russian Workshop on Electron Devices and Materials (EDM)

作者： Minh Sao Khue Luu Santanu Banerjee Evgeniy N. Pavlovskiy Bair N. Tuchinov Stream Data Analytics and Machine Learning Laboratory Novosibirsk State University Novosibirsk Russia Indian Institute of Technology (IIT) Kharagpur Kharagpur West Bengal India

ISBN: (数字)9798350389234

ISBN: (纸本)9798350353051

This study employs three advanced gradient boosting machine learning algorithms to assess potential disparities in healthcare delivery. We specifically investigate which factors contribute to a patient’s timely diagnosis of metastatic breast cancer using a public healthcare dataset. Our approach involves training and testing three separate models, as well as an ensemble model with automatically optimized weights. The models try to predict whether patients received a diagnosis of metastatic breast cancer within 90 days. Each model has different preprocessing and feature selection steps. The hyperparameter optimization is performed using the Optuna library in Python. Models are evaluated on the Kaggle platform, with our metrics indicating strong predictive performance; Categorical Boosting achieved an Area Under the Receiver Operating Characteristic Curve score of 0.813, Extreme Gradient Boosting reached 0.808, Light Gradient Boosting machine scored 0.805, and the ensemble model culminated at 0.808. Additionally, we analyze the set of features being used by all the best models and examine the impact of hyperparameters on the models’ overall performance.

关键词： Measurement Training Analytical models Codes Hospitals Predictive models Boosting

来源：评论

学校读者我要写书评

暂无评论

p-value adjustment for monotonous, unbiased, and fast clustering comparison 23

p-value adjustment for monotonous, unbiased, and fast cluste...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Kai Klede Thomas Altstidl Dario Zanca Björn Eskofier Machine Learning and Data Analytics (MaD) Lab Friedrich-Alexander Universität Erlangen-Nürnberg Machine Learning and Data Analytics (MaD) Lab Friedrich-Alexander Universität Erlangen-Nürnberg and Translational Digital Health Group Institute of AI for Health Helmholtz Zentrum München

Popular metrics for clustering comparison, like the Adjusted Rand Index and the Adjusted Mutual Information, are type II biased. The Standardized Mutual Information removes this bias but suffers from counterintuitive non-monotonicity and poor computational efficiency. We introduce the p-value adjusted Rand Index (PMI2), the first cluster comparison method that is type II unbiased and provably monotonous. The PMI2 has fast approximations that outperform the Standardized Mutual information. We demonstrate its unbiased clustering selection, approximation quality, and runtime efficiency on synthetic benchmarks. In experiments on image and social network datasets, we show how the PMI2 can help practitioners choose better clustering and community detection algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting Influential Higher-Order Patterns in Temporal Network data 14

Predicting Influential Higher-Order Patterns in Temporal Net...

引用

14th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2022

作者： Gote, Christoph Perri, Vincenzo Scholtes, Ingo Data Analytics Group University of Zurich Zurich Switzerland Eth Zurich Systems Design Switzerland Julius-Maximilians-Universität Würzburg Chair of Machine Learning for Complex Networks Würzburg Germany

ISBN: (纸本)9781665456616

Networks are frequently used to model complex systems comprised of interacting elements. While edges capture the topology of direct interactions, the true complexity of many systems originates from higher-order patterns in paths by which nodes can indirectly influence each other. Path data, representing ordered sequences of consecutive direct interactions, can be used to model these patterns. On the one hand, to avoid overfitting, such models should only consider those higher-order patterns for which the data provide sufficient statistical evidence. On the other hand, we hypothesise that network models, which capture only direct interactions, underfit higher-order patterns present in data. Consequently, both approaches are likely to misidentify influential nodes in complex networks. We contribute to this issue by proposing five centrality measures based on MOGen, a multi-order generative model that accounts for all indirect influences up to a maximum distance but disregards influences at higher distances. We compare MOGen-based centralities to equivalent measures for network models and path data in a prediction experiment where we aim to identify influential nodes in out-of-sample data. Our results show strong evidence supporting our hypothesis. MOGen consistently outperforms both the network model and path-based prediction. We further show that the performance difference between MOGen and the path-based approach disappears if we have sufficient observations, confirming that the error is due to overfitting. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

NC-ALG: Graph-Based Active learning under Noisy Crowd 40

NC-ALG: Graph-Based Active Learning under Noisy Crowd

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Zhang, Wentao Wang, Yexin You, Zhenbang Li, Yang Cao, Gang Yang, Zhi Cui, Bin Center for Machine Learning Research Peking University China Key Lab of High Confidence Software Technologies Peking University China Institute of Advanced Algorithms Research Shanghai China Institute of Computational Social Science Peking University Qingdao China National Engineering Labratory for Big Data Analytics and Applications China TEG Tencent Inc. Department of Data Platform China Beijing Academy of Artificial Intelligence China

ISBN: (纸本)9798350317152

Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active learning (AL) methods, they assume that the annotated labels are always correct, which is contradictory to the error-prone labeling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the labeling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node labeling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node labeling, NC-ALG significantly reduces the labeling cost by considering the model-predicted labels and the labels of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms labeling efficiency. Notably, it only takes NC-ALG one-third of the labeling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed. © 2024 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：